Related papers: Data Augmentation Methods for Anaphoric Zero Prono…
End-to-end automatic speech recognition often degrades on domain-specific data due to scarce in-domain resources. We propose a synthetic-data-based domain adaptation framework with two contributions: (1) a large language model (LLM)-based…
Zero-shot domain adaptation for dialogue state tracking (DST) remains a challenging problem in task-oriented dialogue (TOD) systems, where models must generalize to target domains unseen at training time. Current large language model…
Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…
In this paper, a supervised learning technique for extracting keyphrases of Arabic documents is presented. The extractor is supplied with linguistic knowledge to enhance its efficiency instead of relying only on statistical information such…
Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…
Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present…
Speech emotion recognition is an important component of any human centered system. But speech characteristics produced and perceived by a person can be influenced by a multitude of reasons, both desirable such as emotion, and undesirable…
This paper proposes a novel pipeline for automatic grammar augmentation that provides a significant improvement in the voice command recognition accuracy for systems with small footprint acoustic model (AM). The improvement is achieved by…
Language models are vulnerable to short adversarial suffixes that can reliably alter predictions. Previous works usually find such suffixes with gradient search or rule-based methods, but these are brittle and often tied to a single task or…
Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, designing label-preserving transformations for text data tends…
Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data…
Semantic parsing datasets are expensive to collect. Moreover, even the questions pertinent to a given domain, which are the input of a semantic parsing system, might not be readily available, especially in cross-domain semantic parsing.…
Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…
Translation to or from low-resource languages LRLs poses challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing large amounts of monolingual data is regarded as an effective way to alleviate…
The automatic recognition of pathological speech, particularly from children with any articulatory impairment, is a challenging task due to various reasons. The lack of available domain specific data is one such obstacle that hinders its…
Data augmentation is crucial to make machine learning models more robust and safe. However, augmenting data can be challenging as it requires generating diverse data points to rigorously evaluate model behavior on edge cases and mitigate…
Annotation noise is widespread in datasets, but manually revising a flawed corpus is time-consuming and error-prone. Hence, given the prior knowledge in Pre-trained Language Models and the expected uniformity across all annotations, we…
Data augmentation is a ubiquitous technique used to provide robustness to automatic speech recognition (ASR) training. However, even as so much of the ASR training process has become automated and more "end-to-end", the data augmentation…
Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time. Our aim is to teach a pre-trained MT model to…
Augmentation is an effective alternative to utilize the small amount of labeled protein data. However, most of the existing work focuses on design-ing new architectures or pre-training tasks, and relatively little work has studied data…